在k8s上部署sesson模式的flink集群遇到jobmanager报如下错误,请问这是什么原因造成的?要如何fix?
2021-02-07 08:21:41,873 INFO org.apache.flink.runtime.rpc.akka.AkkaRpcService [] - Starting RPC endpoint for org.apache.flink.runtime.dispatcher.StandaloneDispatcher at akka://flink/user/rpc/dispatcher_1 . 2021-02-07 08:21:43,506 WARN org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint [] - Unhandled exception java.io.IOException: Connection reset by peer at sun.nio.ch.FileDispatcherImpl.read0(Native Method) ~[?:1.8.0_275] at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.read(IOUtil.java:192) ~[?:1.8.0_275] at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379) ~[?:1.8.0_275] at org.apache.flink.shaded.netty4.io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:253) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1133) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:350) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:148) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:650) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:576) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) [flink-dist_2.12-1.12.0.jar:1.12.0] at java.lang.Thread.run(Thread.java:748) [?:1.8.0_275] 2021-02-07 08:21:43,940 WARN org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint [] - Unhandled exception java.io.IOException: Connection reset by peer at sun.nio.ch.FileDispatcherImpl.read0(Native Method) ~[?:1.8.0_275] at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.read(IOUtil.java:192) ~[?:1.8.0_275] at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379) ~[?:1.8.0_275] at org.apache.flink.shaded.netty4.io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:253) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1133) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:350) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:148) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:650) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:576) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) [flink-dist_2.12-1.12.0.jar:1.12.0] at java.lang.Thread.run(Thread.java:748) [?:1.8.0_275] |
我也遇到这个问题,集群可以提交正常提交任务,但是jobmanager的日志一直有这个, 请问可有办法解决?
发件人: casel.chen 发送时间: 2021-02-07 16:33 收件人: [hidden email] 主题: flink 1.12.0 k8s session部署异常 在k8s上部署sesson模式的flink集群遇到jobmanager报如下错误,请问这是什么原因造成的?要如何fix? 2021-02-07 08:21:41,873 INFO org.apache.flink.runtime.rpc.akka.AkkaRpcService [] - Starting RPC endpoint for org.apache.flink.runtime.dispatcher.StandaloneDispatcher at akka://flink/user/rpc/dispatcher_1 . 2021-02-07 08:21:43,506 WARN org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint [] - Unhandled exception java.io.IOException: Connection reset by peer at sun.nio.ch.FileDispatcherImpl.read0(Native Method) ~[?:1.8.0_275] at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.read(IOUtil.java:192) ~[?:1.8.0_275] at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379) ~[?:1.8.0_275] at org.apache.flink.shaded.netty4.io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:253) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1133) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:350) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:148) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:650) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:576) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) [flink-dist_2.12-1.12.0.jar:1.12.0] at java.lang.Thread.run(Thread.java:748) [?:1.8.0_275] 2021-02-07 08:21:43,940 WARN org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint [] - Unhandled exception java.io.IOException: Connection reset by peer at sun.nio.ch.FileDispatcherImpl.read0(Native Method) ~[?:1.8.0_275] at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) ~[?:1.8.0_275] at sun.nio.ch.IOUtil.read(IOUtil.java:192) ~[?:1.8.0_275] at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379) ~[?:1.8.0_275] at org.apache.flink.shaded.netty4.io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:253) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1133) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:350) ~[flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:148) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:650) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:576) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) [flink-dist_2.12-1.12.0.jar:1.12.0] at org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) [flink-dist_2.12-1.12.0.jar:1.12.0] at java.lang.Thread.run(Thread.java:748) [?:1.8.0_275] |
这个问题的根本原因是云上LoadBalancer一直在给Flink创建的service发送RST包导致了
这个JIRA[1]可以了解更多信息 临时绕过去的方案就是在log4j2配置里面把org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint这个类的log级别调到ERROR [1]. https://issues.apache.org/jira/browse/FLINK-18129 Best, Yang [hidden email] <[hidden email]> 于2021年3月24日周三 下午5:45写道: > 我也遇到这个问题,集群可以提交正常提交任务,但是jobmanager的日志一直有这个, 请问可有办法解决? > > > 发件人: casel.chen > 发送时间: 2021-02-07 16:33 > 收件人: [hidden email] > 主题: flink 1.12.0 k8s session部署异常 > 在k8s上部署sesson模式的flink集群遇到jobmanager报如下错误,请问这是什么原因造成的?要如何fix? > > > 2021-02-07 08:21:41,873 INFO > org.apache.flink.runtime.rpc.akka.AkkaRpcService [] - Starting > RPC endpoint for org.apache.flink.runtime.dispatcher.StandaloneDispatcher > at akka://flink/user/rpc/dispatcher_1 . > 2021-02-07 08:21:43,506 WARN > org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint [] - Unhandled > exception > java.io.IOException: Connection reset by peer > at sun.nio.ch.FileDispatcherImpl.read0(Native Method) > ~[?:1.8.0_275] > at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) > ~[?:1.8.0_275] > at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) > ~[?:1.8.0_275] > at sun.nio.ch.IOUtil.read(IOUtil.java:192) ~[?:1.8.0_275] > at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379) > ~[?:1.8.0_275] > at > org.apache.flink.shaded.netty4.io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:253) > ~[flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1133) > ~[flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:350) > ~[flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:148) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:650) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:576) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at java.lang.Thread.run(Thread.java:748) [?:1.8.0_275] > 2021-02-07 08:21:43,940 WARN > org.apache.flink.runtime.dispatcher.DispatcherRestEndpoint [] - Unhandled > exception > java.io.IOException: Connection reset by peer > at sun.nio.ch.FileDispatcherImpl.read0(Native Method) > ~[?:1.8.0_275] > at sun.nio.ch.SocketDispatcher.read(SocketDispatcher.java:39) > ~[?:1.8.0_275] > at sun.nio.ch.IOUtil.readIntoNativeBuffer(IOUtil.java:223) > ~[?:1.8.0_275] > at sun.nio.ch.IOUtil.read(IOUtil.java:192) ~[?:1.8.0_275] > at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:379) > ~[?:1.8.0_275] > at > org.apache.flink.shaded.netty4.io.netty.buffer.PooledByteBuf.setBytes(PooledByteBuf.java:253) > ~[flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.buffer.AbstractByteBuf.writeBytes(AbstractByteBuf.java:1133) > ~[flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doReadBytes(NioSocketChannel.java:350) > ~[flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:148) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:714) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:650) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:576) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:493) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:989) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at > org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) > [flink-dist_2.12-1.12.0.jar:1.12.0] > at java.lang.Thread.run(Thread.java:748) [?:1.8.0_275] > |
Free forum by Nabble | Edit this page |